arXiv Machine Learning July 7, 2026 By Oussama Draissi, Mark G\"unzel, Ahmad-Reza Sadeghi, Lucas Davi

Walma: Learning to See Memory Corruption in WebAssembly

Read the original on arXiv Machine Learning →

arXiv:2603. 24167v2 Announce Type: replace-cross Abstract: WebAssembly's (Wasm) monolithic linear memory turns a single memory-corruption bug into a bidirectional threat: a compromised module can attack its embedding host, and a malicious host can tamper with a trusted module's state.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 9

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

arXiv:2604. 17249v2 Announce Type: replace-cross Abstract: Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target.

By Yuji Yamamoto, Satoshi Matsuura

llms safety

arXiv AI

Aug 5

Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents

arXiv:2605. 08442v5 Announce Type: replace-cross Abstract: We discover that prompt-injection success and tool-execution success are separable safety properties: defenses that block injection do not necessarily block execution, and vice versa.

By Jun Wen Leong

llms rag agents benchmarks safety

arXiv Machine Learning

Jun 10

MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents

arXiv:2606. 10742v1 Announce Type: cross Abstract: External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences.

By Yv Zhang, Hao Sun, Hao Fang, Kuofeng Gao, Fan Mo, Bin Chen, Shu-Tao Xia, Yaowei Wang

llms agents computer-vision multimodal safety

arXiv AI

Jul 31

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.

By Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou, Shanqing Yu, Qi Xuan

llms agents benchmarks

arXiv AI

Jul 17

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

arXiv:2607. 14651v1 Announce Type: cross Abstract: Persistent external memory enhances agent continuity but introduces persistent security vulnerabilities: adversarial content can be injected via standard interaction channels, retained across turns, and later distort downstream behavior.

By Jifeng Gao, Kang Xia, Yi Zhang, Xiaobin Hong, Mingkai Lin, Xingshen Wei, Wenzhong Li, Sanglu Lu

llms agents benchmarks safety

arXiv AI

Jul 7

JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode

arXiv:2607. 02825v1 Announce Type: cross Abstract: We release \textsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection.

By Norbert Sandor Szolnoki, Gabor Antal

llms fine-tuning benchmarks

Related stories

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents

MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

MemPoison: Uncovering Persistent Memory Threats and Structural Blind Spots in LLM Agents

JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode